7 citations · 13 across the 4 of their papers we have counts for
4 papers
Task-Adaptive Feature Transformer for Few-Shot Segmentation
Jun Seo, Young-Hyun Park, Sung-Whan Yoon +1
Few-shot learning allows machines to classify novel classes using only a few labeled samples. Recently, few-shot segmentation aiming at semantic segmentation on low sample data has…
CAFENet: Class-Agnostic Few-Shot Edge Detection Network
Young-Hyun Park, Jun Seo, Jaekyun Moon
We tackle a novel few-shot learning challenge, which we call few-shot semantic edge detection, aiming to localize crisp boundaries of novel categories using only a few labeled samp…
Task-Adaptive Clustering for Semi-Supervised Few-Shot Classification
Jun Seo, Sung Whan Yoon, Jaekyun Moon
Few-shot learning aims to handle previously unseen tasks using only a small amount of new training data. In preparing (or meta-training) a few-shot learner, however, massive labele…
XtarNet: Learning to Extract Task-Adaptive Representation for Incremental Few-Shot Learning
Sung Whan Yoon, Do-Yeon Kim, Jun Seo +1
Learning novel concepts while preserving prior knowledge is a long-standing challenge in machine learning. The challenge gets greater when a novel task is given with only a few lab…